TTS
The voice that reads tips on stream - queue, history, voice settings, and AI voices.
The TTS page runs everything about the voice on your stream: the queue of messages waiting to play, the history of what’s played, and the voice itself.
Queue and history
The Queue panel shows what’s waiting, in order. The History panel shows what’s already played, with a replay button - great for “wait, what did that say?” moments. Replayed tips show a gold “(Replay)” badge on the overlay so chat knows it’s a rerun.
Voice settings
These settings shape the audio that gets generated for every tip:
- TTS enabled - the master switch for generating tip audio.
- Language - the voice, e.g. English (UK).
- Read donor names / amounts / messages - three toggles for what gets spoken. Turn amounts off if you don’t want numbers read out.
- Preview - plays a sample so you can tune it without firing test alerts.
Playback lives with each overlay: the per-overlay TTS toggle, volume, and the tip alert sound (including uploading and picking sound files) are all in the overlay editor, so two overlays can behave differently.
Viewers get a Preview TTS button on your tip page too, so they hear exactly how their message will sound before paying. Same voice, same settings.
AI voices (closed beta)
Accounts in the AI voices beta get an extra AI voices panel on the TTS page. When it’s on, viewers can have their tip read out in AI voices instead of the standard one - and they can write a script, where different lines of the message are spoken by different voices, played back-to-back as one clip.
On the tip page, viewers see a “Read it in AI voices” button under the message box. It opens a script editor: each line has a voice attached, tapping the voice name opens a picker with a playable sample for every voice, and pressing Enter starts the next line for a back-and-forth.
Your controls in the panel:
- Offer AI voices to donors - the master switch.
- Mode - Donors can choose keeps the standard voice as the default, with AI voices as an option. All TTS uses AI voices removes the standard voice entirely: every tip message is AI-voiced.
- Minimum tip for AI voices - set it equal to your minimum tip for no extra requirement, or higher to make AI voices a premium that viewers unlock by tipping more.
- Voices - pick which voices viewers can choose from, with a play button to sample each one. Everything’s enabled by default.
- Character budget - AI generation spends characters from a monthly allowance. The meter shows what’s left; when it runs out, AI voices pause (viewers fall back to the standard voice) until the month rolls over.
A few things to know:
- Free messages can use AI voices too - but only while you haven’t set a higher minimum tip for them. A free message can’t clear a paid gate.
- Your word filter and AI tip filter still apply. If a filter changes the message, the AI audio speaks the filtered text - or falls back to the standard voice if it can’t.
- AI audio takes a little longer to generate than standard TTS, especially multi-voice scripts. The overlay holds the tip at the front of the queue until its audio is ready rather than playing it in the wrong voice.
- There’s no message preview for AI voices - generation is metered - but every voice has a sample clip viewers can play before choosing.
- Automating it? The developer API can read the catalog and toggle the feature or individual voices.
AI voices are invite-only while in beta - if the panel isn’t on your TTS page, your account isn’t flagged in yet.
Mod control from chat
Your mods don’t need dashboard access to run the queue - !tts skip, !tts pause, !tts resume, and !tts replay all work from chat once the bot is enabled.